Universal probability-free prediction. / Vovk, Vladimir; Pavlovic, Dusko.

In: Annals of Mathematics and Artificial Intelligence, Vol. 81, No. 1-2, 10.2017, p. 1-24.

Research output: Contribution to journalArticle

Published

Standard

Universal probability-free prediction. / Vovk, Vladimir; Pavlovic, Dusko.

In: Annals of Mathematics and Artificial Intelligence, Vol. 81, No. 1-2, 10.2017, p. 1-24.

Research output: Contribution to journalArticle

Harvard

Vovk, V & Pavlovic, D 2017, 'Universal probability-free prediction', Annals of Mathematics and Artificial Intelligence, vol. 81, no. 1-2, pp. 1-24. https://doi.org/10.1007/s10472-017-9547-9

APA

Vovk, V., & Pavlovic, D. (2017). Universal probability-free prediction. Annals of Mathematics and Artificial Intelligence, 81(1-2), 1-24. https://doi.org/10.1007/s10472-017-9547-9

Vancouver

Vovk V, Pavlovic D. Universal probability-free prediction. Annals of Mathematics and Artificial Intelligence. 2017 Oct;81(1-2):1-24. https://doi.org/10.1007/s10472-017-9547-9

Author

Vovk, Vladimir ; Pavlovic, Dusko. / Universal probability-free prediction. In: Annals of Mathematics and Artificial Intelligence. 2017 ; Vol. 81, No. 1-2. pp. 1-24.

BibTeX

@article{d302b1785c274c90a28d512f277f7231,
title = "Universal probability-free prediction",
abstract = "We construct universal prediction systems in the spirit of Popper's falsifiability and Kolmogorov complexity and randomness. These prediction systems do not depend on any statistical assumptions (but under the IID assumption they dominate, to within the usual accuracy, conformal prediction). Our constructions give rise to a theory of algorithmic complexity and randomness of time containing analogues of several notions and results of the classical theory of Kolmogorov complexity and randomness.",
keywords = "Conformal prediction, Prediction systems, Probability-free learning, Universal prediction",
author = "Vladimir Vovk and Dusko Pavlovic",
year = "2017",
month = oct,
doi = "10.1007/s10472-017-9547-9",
language = "English",
volume = "81",
pages = "1--24",
journal = "Annals of Mathematics and Artificial Intelligence",
issn = "1012-2443",
publisher = "Springer Netherlands",
number = "1-2",

}

RIS

TY - JOUR

T1 - Universal probability-free prediction

AU - Vovk, Vladimir

AU - Pavlovic, Dusko

PY - 2017/10

Y1 - 2017/10

N2 - We construct universal prediction systems in the spirit of Popper's falsifiability and Kolmogorov complexity and randomness. These prediction systems do not depend on any statistical assumptions (but under the IID assumption they dominate, to within the usual accuracy, conformal prediction). Our constructions give rise to a theory of algorithmic complexity and randomness of time containing analogues of several notions and results of the classical theory of Kolmogorov complexity and randomness.

AB - We construct universal prediction systems in the spirit of Popper's falsifiability and Kolmogorov complexity and randomness. These prediction systems do not depend on any statistical assumptions (but under the IID assumption they dominate, to within the usual accuracy, conformal prediction). Our constructions give rise to a theory of algorithmic complexity and randomness of time containing analogues of several notions and results of the classical theory of Kolmogorov complexity and randomness.

KW - Conformal prediction

KW - Prediction systems

KW - Probability-free learning

KW - Universal prediction

U2 - 10.1007/s10472-017-9547-9

DO - 10.1007/s10472-017-9547-9

M3 - Article

VL - 81

SP - 1

EP - 24

JO - Annals of Mathematics and Artificial Intelligence

JF - Annals of Mathematics and Artificial Intelligence

SN - 1012-2443

IS - 1-2

ER -